Multi-Goal Reinforcement Learning
17 papers with code • 0 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Multi-Goal Reinforcement Learning
UniMiB SHAR
bipedal-skills
Latest papers with no code
Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective
Intuitively, learning from those arbitrary demonstrations can be seen as a form of imitation learning (IL).
Cluster-based Sampling in Hindsight Experience Replay for Robotic Tasks (Student Abstract)
The proposed sampling strategy groups episodes with different achieved goals by using a cluster model and samples experiences in the manner of HER to create the training batch.
Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time.
Bi-linear Value Networks for Multi-goal Reinforcement Learning
We simultaneously learn both components.
MHER: Model-based Hindsight Experience Replay
Replacing original goals with virtual goals generated from interaction with a trained dynamics model leads to a novel relabeling method, model-based relabeling (MBR).
Unbiased Methods for Multi-Goal Reinforcement Learning
We introduce unbiased deep Q-learning and actor-critic algorithms that can handle such infinitely sparse rewards, and test them in toy environments.
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency.
MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications.
Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback
Lastly, we enable the learning of complex, sequential, tasks using a form of curriculum learning combined with HER.
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn.
